Security audit

Writing Credibility Auditor

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward writing-audit skill that analyzes user-provided text and does not request tools, credentials, network access, persistence, or broad local data access.

This skill appears safe to install for credibility audits of writing. Users should understand that it is not a live fact-checker, does not verify current facts against sources, and works best on English-language text.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The instructions state 'I can audit this most reliably in English' and require user confirmation before proceeding in another detected language. This establishes English as the default operating language rather than offering a neutral language choice up front, which can be a locale/language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.